© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201007
    Prev
    Next
    INDEX
    Explanations

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite

    handle common cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hogares
    0.45
     directement
    0.44
     directamente
    0.43
    ⠊
    0.43
    ँग्रेस
    0.42
     prostit
    0.42
     QTreeWidgetItem
    0.42
    )^\
    0.42
    marginY
    0.42
     individuais
    0.42
    POSITIVE LOGITS
    he
    0.53
    in
    0.53
    es
    0.50
     time
    0.50
    ेंद्र
    0.49
     koska
    0.48
    because
    0.46
    After
    0.46
    as
    0.45
    after
    0.44
    Activations Density 0.000%

    No Known Activations